Training in progress, step 14000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:04edd0da12c2a2601bd775ffcf352668519673235c7a5d7ae593397ac22122e1
|
3 |
size 242041896
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484163514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ceb64fd4cbdba95fc70210cf5ed8b0979a4dfac5bd686bddb15358c56e4acc56
|
3 |
size 484163514
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b64855e1cbb26f48a5b6040284fea1a822a0bde261907a0405daabf13ee791d6
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e142a6be921f20ce4151d406be94766e7ee360e6fc05f8c379d00e4681c45917
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -189,13 +189,19 @@
|
|
189 |
"learning_rate": 0.0005857888275015347,
|
190 |
"loss": 0.5307,
|
191 |
"step": 13500
|
|
|
|
|
|
|
|
|
|
|
|
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 500,
|
195 |
"max_steps": 32580,
|
196 |
"num_train_epochs": 5,
|
197 |
"save_steps": 500,
|
198 |
-
"total_flos":
|
199 |
"trial_name": null,
|
200 |
"trial_params": null
|
201 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.1485573971761815,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 14000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
189 |
"learning_rate": 0.0005857888275015347,
|
190 |
"loss": 0.5307,
|
191 |
"step": 13500
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.15,
|
195 |
+
"learning_rate": 0.0005704419889502763,
|
196 |
+
"loss": 0.5325,
|
197 |
+
"step": 14000
|
198 |
}
|
199 |
],
|
200 |
"logging_steps": 500,
|
201 |
"max_steps": 32580,
|
202 |
"num_train_epochs": 5,
|
203 |
"save_steps": 500,
|
204 |
+
"total_flos": 7420232689778688.0,
|
205 |
"trial_name": null,
|
206 |
"trial_params": null
|
207 |
}
|